consultance.ai
Business operations

The Strategy Analyst Pack

A McKinsey engagement runs into six figures and a room of analysts, and AI already does about 40 percent of that analyst's work per Forrester. This runs the analyst layer of a strategy engagement on your own inputs, in your own Claude. 8 prompts build the market entry analysis, the competitor teardown, the synergy or business case with base, downside, and upside, the expert-call synthesis, a self-check that re-derives every number, the board deck outline, and the recommendation memo. The work a team of analysts drafts over six weeks, in an afternoon, with a named human applying the judgment.

Rent it forever, or own it once.

A McKinsey engagement runs into six figures and a room of analysts, and AI already does about 40 percent of that analyst's work per Forrester

Step 1

Paste this setup prompt — Claude installs it for you

Easy mode · paste this into Claude

Claude installs it for you, step by step.

Never used Claude before? It is free to start. Open it in a new tab, copy the prompt, paste it in. It asks one question, then walks you through everything.

  1. Step 1
    Open claude.ai ↗

    Sign up free. No card. Takes 30 seconds.

  2. Step 2

    One click. Lands on your clipboard.

  3. Step 3
    Paste + send

    Claude asks what you need + guides you the rest of the way.

Open claude.ai ↗
Tune the prompt for your level (optional)
Preview the prompt (you do not need to read it)
I want to set this up properly so Claude runs the analyst layer of a strategy engagement on my real inputs, not a one-off chat. Walk me through it step by step, do not skip anything. Treat me like a founder, operator, or strategy lead who has never built a Claude Project and does not write code. Define every term once.

This is NOT a Terminal or coding install. There is nothing to compile. It is a private Claude Project where the market data and the brief live.

## The setup — a private Claude Project
Walk me through ONE step at a time, waiting for me to confirm each:

1. **What I need.** A Claude account on a paid plan so I can pin the better model. Pin **Opus 4.8**. Nothing to install.
2. **Make the workspace.** In Claude, create a new **Project** named for the decision or the deal. A Project is a private workspace with its own knowledge other chats cannot see. My data stays in my own tenant.
3. **Load the inputs.** Drop in whatever I have: market reports, competitor info, financials, expert-call notes, and the brief. If I am thin on data, that is fine, the prompts will flag what is missing instead of inventing it.
4. **Run the vault.** Run prompt 01, pick what I am running (market entry, competitor teardown, business case, or the full board readout) and where my data is. Then run 02 to 08: market entry, competitor teardown, the business case, the synthesis, the self-check, the board deck outline, and the recommendation memo.
5. **Gate it.** Treat prompt 06 (the self-check) as a hard stop. A **GATE: FAILED** means a number did not reconcile; fix it before the board deck. This is decision support, not the decision. A named executive owns the call.

## Rules for walking me through this
- One step at a time. Define every term once: Project, knowledge, market sizing, segment, entry barrier, business case, payback, base/downside/upside case, synthesis, review gate.
- Do NOT tell me a step is "not possible." If I cannot find the Project button, it is in the left sidebar of claude.ai.
- The prompts must never invent a market number. If the data is not there, they flag it.
- This does the analyst work; a named human applies judgment and decides. Not investment or legal advice.

First message: ask me "What are you running: a market entry analysis, a competitor teardown, a business case, or the full board readout? And what inputs do you have to upload?" Then start step 1.
Step 2

Step 1 installed it. Now run these 8 prompts on your own data.

the vault

The 8 prompts

Tap a prompt to jump to it. Hit copy. Replace the tokens. Paste into Claude Opus 4.7.

where it breaks

Before you connect live data

  • • Run dummy data first. Real client data is not a test bed.
  • • API keys never go in a public repo. Use env vars and a secrets manager.
  • • Add logging, access control, monitoring, and a rollback path before launch.
  • • Read the license. Forking a repo without checking is how lawsuits start.
license note

Credit the original author

Prompt set authored by consultance.ai. McKinsey, Bain, and BCG are referenced as the standard the pack matches, no affiliation implied. Your data stays in your own Claude tenant; we never see it. This produces decision support, not the decision; a named executive owns the call and the prompts never invent a market number. Not investment or legal advice.

the newsletter

AI news worth opening.

The AI tools, launches, and shifts that actually matter, in plain English. New library drops the moment they land.

100% freeNo paywall, everUnsubscribe anytime

Want this running in your business, not just your laptop? We build it and hand you the keys.